Pith. sign in

REVIEW 6 cited by

Motion Anything: Any to Motion Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.06955 v2 pith:AOWHCTZE submitted 2025-03-10 cs.CV

Zeyu Zhang , Yiran Wang , Wei Mao , Danning Li , Rui Zhao , Biao Wu , Zirui Song , Bohan Zhuang
show 2 more authors
Ian Reid Richard Hartley
This is my paper · ORCID
classification cs.CV
keywords motionanythinggenerationmethodsaistchallengesconditionscontrol
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models lack a mechanism to prioritize dynamic frames and body parts based on given conditions. Second, existing methods for different conditioning modalities often fail to integrate multiple modalities effectively, limiting control and coherence in generated motion. To address these challenges, we propose Motion Anything, a multimodal motion generation framework that introduces an Attention-based Mask Modeling approach, enabling fine-grained spatial and temporal control over key frames and actions. Our model adaptively encodes multimodal conditions, including text and music, improving controllability. Additionally, we introduce Text-Music-Dance (TMD), a new motion dataset consisting of 2,153 pairs of text, music, and dance, making it twice the size of AIST++, thereby filling a critical gap in the community. Extensive experiments demonstrate that Motion Anything surpasses state-of-the-art methods across multiple benchmarks, achieving a 15% improvement in FID on HumanML3D and showing consistent performance gains on AIST++ and TMD. See our project website https://steve-zeyu-zhang.github.io/MotionAnything

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Kinetic Mining in Context: Few-Shot Action Synthesis via Text-to-Motion Distillation

    cs.CV 2025-12 conditional novelty 7.0 of 10

    A CLIP-guided teacher-student pipeline distills a text-to-motion prior into a few-shot action-to-motion generator, improving HAR top-1 accuracy by 23.1 points on 3 NTU-120 classes.

  2. Absolute Coordinates Make Motion Generation Easy

    cs.CV 2025-05 conditional novelty 7.0 of 10

    Using absolute 3D joint coordinates with a plain Transformer and velocity-prediction diffusion outperforms the standard local-relative motion representation, improving fidelity and enabling direct control.

  3. Interactive Generative Motion Editing via Scheduled Inpainting

    cs.GR 2026-07 conditional novelty 6.0 of 10

    Scheduled inpainting blends a base motion clip into a diffusion model's denoising process via a user-controlled schedule and spatiotemporal mask, enabling interactive editing of existing animations without retraining.

  4. Language-Guided Transformer Tokenizer for Human Motion Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Injecting language into the motion tokenizer yields more compact semantic tokens and state-of-the-art generation scores on HumanML3D and Motion-X.

  5. ST-GDance: Long-Term and Collision-Free Group Choreography from Music

    cs.AI 2025-07 conditional novelty 6.0 of 10

    ST-GDance decouples spatial and temporal modeling, using a distance-aware graph to avoid collisions and sparse attention to cut compute, improving long-sequence group dance generation.

  6. PresentAgent: Multimodal Agent for Presentation Video Generation

    cs.CV 2025-07 reject novelty 5.0 of 10

    PresentAgent chains LLM segmentation, slide rendering, TTS, and ffmpeg to turn documents into narrated presentation videos, but the human-level claim rests on five documents and an unvalidated VLM judge.

Pith tools